Klasifikacija moždanih tumora metodama dubokog učenja na temelju snimki magnetske rezonancije

undergraduate thesis

• Title (english): Brain tumor classification using deep learning methods based on magnetic resonance imaging
• Author: Katarina Šabić
• Mentor: Alan Jović (mentor)
• Committee member: Alan Jović (predsjednik povjerenstva)
• Committee member: Nikolina Frid (član povjerenstva)
• Committee member: Adrian Satja Kurdija (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2023-08-29, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Ovaj rad prikazuje primjenu dubokog učenja, odnosno konvolucijskih neuronskih mreža u rješavanju klasifikacijskog problema u području medicinske dijagnostike. Prikazana je izgradnja dva modela neuronskih mreža i analizirane su razlike u njihovoj građi koje utječu na performanse i dobivene rezultate. Rezultati učenja neuronskih mreža dani su u obliku funkcija gubitka i preciznosti, i matrice konfuzije. Postignuta je točnost klasifikacije četiri klase moždanih tumora od preko 93% koristeći konvolucijski model.

Abstract (english)

This paper shows the application of deep learning, respectively convolutional neural networks in solving the classification problem in the field of medical diagnostics. It shows the building of the two models of neural networks, and analyses the differences in their structure, which affect the performance and the obtained results. The learning results of the neural networks are given in the form of loss and precision functions, and the confusion matrix. The classification accuracy of four classes of brain tumors of over 93% was achieved using the convolutional model.

• Keywords: Umjetna inteligencija; duboko učenje; konvolucijske neuronske mreže; klasifikacija slika
• Keywords (english): Artificial intelligence; deep learning; convolutional neural networks; image classification
• Language: croatian
• URN:NBN: urn:nbn:hr:168:440845
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-10-11 10:35:45